Alberto Del Bimbo Multimedia and Computer Vision

Alberto Del Bimbo

Alberto del Bimbo is Professor of Computer Engineering at the Department of Information Engineering, University of Firenze and Director of MICC Media Integration and Communication Center, University of Firenze.

Prof. Alberto del Bimbo leads a research team at MICC, Media Integration and Communication Center of University of Firenze, investigating cutting-edge solutions in the fields of multimedia, multimodal interactivity and computer vision.

The main applications fields in his research include digital libraries and cultural heritage, user enhanced and personalized interactivity, smart environments, surveillance and monitoring, and industry automation.

In the field of Multimedia, Prof. Del Bimbo was one of the very first researchers to start research in image and video content-based retrieval in the late 80’s. He is the author of the monography, Visual Information Retrieval, edited by Morgan Khaufman in 1999, which became one of the most cited books in the early times of image and video content-based retrieval (over 1000 citations).

In 2010, the team leaded by Prof. Del Bimbo contributed to the EC VidiVideo project, led by the University of Amsterdam, on automatic recognition of 1000 concepts. Recently in 2016, he coauthored a comprehensive survey on automatic annotation and retrieval of Social Media, which appeared on ACM Computing Surveys, the most prestigeous journal in computer Science.

In the field of Computer Vision, Prof. Del Bimbo has worked actively over 20 years in tracking and surveillance applications and more in general in industrial applications with important collaborations with national and international companies, such as Leonardo Finmeccanica, Panasonic Singapore, Thales Italia and the US IARPA agency, just to cite the most recent and ongoing collaborations.

Prof. Del Bimbo published about 400 refereed research papers in the most prestigeous scientific Journals and Conference Proceedings. The list of publication is available at https://scholar.google.com/ [Del Bimbo Alberto]

Indexing quantized ensembles of exemplar-SVMs with rejecting taxonomies

F. Becattini, L. Seidenari, A. Del Bimbo

Multimedia Tools and Applications, 2017

Efficient and compact visual feature descriptors hashing using hierarchical multiple assignment k-means

S. Ercoli, M. Bertini, A. Del Bimbo

Proc. of IEEE International Conference on Multimedia & Expo Workshops(ICMEW), 2017

Reading text in the wild from compressed images

L. Galteri, D. Bazazian, L. Seidenari, M. Bertini, A. D. Bagdanov, A. Nicolau, D. Karatzas, A. Del Bimbo

Proc. of IEEE International Conference on Computer Vision workshops (ICCV), 2017

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

S. Ercoli, M. Bertini, A. Del Bimbo

IEEE Transactions on Multimedia, 2017

2017

Deep generative adversarial compression artifact removal

L. Galteri, L. Seidenari, M. Bertini, A. Del Bimbo

Proc. of International Conference on Computer Vision (ICCV), 2017

A Dictionary Learning Based 3D Morphable Shape Model

C. Ferrari, G. Lisanti, S. Berretti, A. Del Bimbo

IEEE Transactions on Multimedia, 2017

Web video popularity prediction using sentiment and content visual features.

G. Fontanini, M. Bertini, A. Del Bimbo

Proc. of ACM International Conference on Multimedia Retrieval (ICMR), 2016